Huggy

Huggy/Huggy-199992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7650e12f076442a2cc0775d863dc2921ca2bcc5af35c62d272a5521ae7f56cbb
+size 2274020

Huggy/Huggy-199992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34a1edc80838403e7e24b363e698b6daeaf62c6b1988b0a620e3ccdc6504790
+size 13509859

Huggy/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d208fd1f09106d81034f43cdd306917f3ffd630ee7ed09f9ee62b4dad376abbf
+size 13509685

Huggy/events.out.tfevents.1763310355.1e5076c78a99.8506.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7a88280002fc1059194aacd382f78e991b3e4800e4c66804aa0a3c640fadb3
+size 14961

README.md

@@ -1,37 +1,35 @@
 ---
-library_name: stable-baselines3
+library_name: ml-agents
 tags:
-- LunarLander-v2
+- Huggy
 - deep-reinforcement-learning
 - reinforcement-learning
-- stable-baselines3
-model-index:
-- name: PPO
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
-    metrics:
-    - type: mean_reward
-      value: 269.91 +/- 19.60
-      name: mean_reward
-      verified: false
+- ML-Agents-Huggy
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  # **ppo** Agent playing **Huggy**
+  This is a trained model of a **ppo** agent playing **Huggy**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
 
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
 
-...
-```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: underspirit/learn-rl
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7c11c52a1260>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c11c52a1300>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c11c52a13a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c11c52a1440>", "_build": "<function ActorCriticPolicy._build at 0x7c11c52a14e0>", "forward": "<function ActorCriticPolicy.forward at 0x7c11c52a1580>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c11c52a1620>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c11c52a16c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c11c52a1760>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c11c52a1800>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c11c52a18a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c11c52a1940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c11c5208d00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1763226638712980923, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdwIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBNudW1weS5fY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolggAAAAAAAAAAQEBAQEBAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBEolggAAAAAAAAAAQEBAQEBAQGUaBVLCIWUaBl0lFKUjAZfc2hhcGWUSwiFlIwDbG93lGgRKJYgAAAAAAAAAAAAtMIAALTCAACgwAAAoMDbD0nAAACgwAAAAIAAAACAlGgLSwiFlGgZdJRSlIwEaGlnaJRoESiWIAAAAAAAAAAAALRCAAC0QgAAoEAAAKBA2w9JQAAAoEAAAIA/AACAP5RoC0sIhZRoGXSUUpSMCGxvd19yZXBylIxbWy05MC4gICAgICAgIC05MC4gICAgICAgICAtNS4gICAgICAgICAtNS4gICAgICAgICAtMy4xNDE1OTI3ICAtNS4KICAtMC4gICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMU1s5MC4gICAgICAgIDkwLiAgICAgICAgIDUuICAgICAgICAgNS4gICAgICAgICAzLjE0MTU5MjcgIDUuCiAgMS4gICAgICAgICAxLiAgICAgICBdlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  Huggy:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 200000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 15
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 1000
+    summary_freq: 50000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./trained-envs-executables/linux/Huggy/Huggy
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Huggy2
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,294 @@
+Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/Managed'
+Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.214 seconds
+ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderLdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderHdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/UberPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Hidden/Universal Render Pipeline/FallbackError shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Hidden/Universal Render Pipeline/Stop NaN shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/SubpixelMorphologicalAntialiasing shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/GaussianDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/BokehDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/CameraMotionBlur shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/PaniniProjection shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Bloom shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/FinalPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Hidden/Universal Render Pipeline/LensFlareDataDriven shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Scaling Setup shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Edge Adaptive Spatial Upsampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Debug/DebugReplacement shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/kMotion/CameraMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/kMotion/ObjectMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.735940 ms
+requesting resize 84 x 84
+Setting up 1 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 2800 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 3.6 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 240 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 296.0 KB
+      Peak Allocated Bytes 211.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 288
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2801 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 22.3 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 2785 frames, [2.0 MB-4.0 MB]: 16 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.3 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2800 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 2801 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 81.8 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 2800 frames, [16.0 MB-32.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 30.6 MB
+      Peak Large allocation bytes 24.9 MB
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2800 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.6 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 2801 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 2801 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.3 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "Huggy.Policy.Entropy.mean": {
+            "value": 1.423821210861206,
+            "min": 1.4190664291381836,
+            "max": 1.423821210861206,
+            "count": 4
+        },
+        "Huggy.Policy.Entropy.sum": {
+            "value": 70047.734375,
+            "min": 68564.7890625,
+            "max": 77754.90625,
+            "count": 4
+        },
+        "Huggy.Environment.EpisodeLength.mean": {
+            "value": 230.05990783410138,
+            "min": 230.05990783410138,
+            "max": 406.8861788617886,
+            "count": 4
+        },
+        "Huggy.Environment.EpisodeLength.sum": {
+            "value": 49923.0,
+            "min": 49478.0,
+            "max": 50080.0,
+            "count": 4
+        },
+        "Huggy.Step.mean": {
+            "value": 199992.0,
+            "min": 49947.0,
+            "max": 199992.0,
+            "count": 4
+        },
+        "Huggy.Step.sum": {
+            "value": 199992.0,
+            "min": 49947.0,
+            "max": 199992.0,
+            "count": 4
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8986622095108032,
+            "min": 0.07460981607437134,
+            "max": 0.8986622095108032,
+            "count": 4
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 195.00970458984375,
+            "min": 9.102397918701172,
+            "max": 195.00970458984375,
+            "count": 4
+        },
+        "Huggy.Environment.CumulativeReward.mean": {
+            "value": 3.2933797877505078,
+            "min": 1.833546322510868,
+            "max": 3.2933797877505078,
+            "count": 4
+        },
+        "Huggy.Environment.CumulativeReward.sum": {
+            "value": 714.6634139418602,
+            "min": 223.69265134632587,
+            "max": 714.6634139418602,
+            "count": 4
+        },
+        "Huggy.Policy.ExtrinsicReward.mean": {
+            "value": 3.2933797877505078,
+            "min": 1.833546322510868,
+            "max": 3.2933797877505078,
+            "count": 4
+        },
+        "Huggy.Policy.ExtrinsicReward.sum": {
+            "value": 714.6634139418602,
+            "min": 223.69265134632587,
+            "max": 714.6634139418602,
+            "count": 4
+        },
+        "Huggy.Losses.PolicyLoss.mean": {
+            "value": 0.014468230124233135,
+            "min": 0.014468230124233135,
+            "max": 0.01799517210521218,
+            "count": 4
+        },
+        "Huggy.Losses.PolicyLoss.sum": {
+            "value": 0.02893646024846627,
+            "min": 0.02893646024846627,
+            "max": 0.05398551631563654,
+            "count": 4
+        },
+        "Huggy.Losses.ValueLoss.mean": {
+            "value": 0.026294824046393238,
+            "min": 0.021919104425857462,
+            "max": 0.028443139636268218,
+            "count": 4
+        },
+        "Huggy.Losses.ValueLoss.sum": {
+            "value": 0.052589648092786476,
+            "min": 0.043838208851714924,
+            "max": 0.07307288901259501,
+            "count": 4
+        },
+        "Huggy.Policy.LearningRate.mean": {
+            "value": 0.000273529283823575,
+            "min": 0.000273529283823575,
+            "max": 0.0002952804015732,
+            "count": 4
+        },
+        "Huggy.Policy.LearningRate.sum": {
+            "value": 0.00054705856764715,
+            "min": 0.00054705856764715,
+            "max": 0.0008437236187587998,
+            "count": 4
+        },
+        "Huggy.Policy.Epsilon.mean": {
+            "value": 0.19117642500000004,
+            "min": 0.19117642500000004,
+            "max": 0.19842680000000001,
+            "count": 4
+        },
+        "Huggy.Policy.Epsilon.sum": {
+            "value": 0.3823528500000001,
+            "min": 0.3823528500000001,
+            "max": 0.5812412,
+            "count": 4
+        },
+        "Huggy.Policy.Beta.mean": {
+            "value": 0.0045597036075,
+            "min": 0.0045597036075,
+            "max": 0.00492149732,
+            "count": 4
+        },
+        "Huggy.Policy.Beta.sum": {
+            "value": 0.009119407215,
+            "min": 0.009119407215,
+            "max": 0.014063935880000003,
+            "count": 4
+        },
+        "Huggy.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4
+        },
+        "Huggy.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1763310354",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1763310613"
+    },
+    "total": 259.3432807009999,
+    "count": 1,
+    "self": 0.4830919629998789,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02540454200016029,
+            "count": 1,
+            "self": 0.02540454200016029
+        },
+        "TrainerController.start_learning": {
+            "total": 258.8347841959999,
+            "count": 1,
+            "self": 0.43272949203264943,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.5080423469999005,
+                    "count": 1,
+                    "self": 3.5080423469999005
+                },
+                "TrainerController.advance": {
+                    "total": 254.8932644569668,
+                    "count": 23689,
+                    "self": 0.45385130094291526,
+                    "children": {
+                        "env_step": {
+                            "total": 215.56824009102093,
+                            "count": 23689,
+                            "self": 171.9124859079966,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 43.37427502898527,
+                                    "count": 23689,
+                                    "self": 1.5959830879937726,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 41.778291940991494,
+                                            "count": 23339,
+                                            "self": 41.778291940991494
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.28147915403906154,
+                                    "count": 23689,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 257.4733873230016,
+                                            "count": 23689,
+                                            "is_parallel": true,
+                                            "self": 118.62030745898437,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.000843426000301406,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002643500006342947,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0005790759996671113,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005790759996671113
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.029022094000083598,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00033737000012479257,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00020290999964345247,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00020290999964345247
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02769276600020021,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02769276600020021
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0007890480001151445,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00022475600007965113,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005642920000354934,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005642920000354934
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 138.85307986401722,
+                                                    "count": 23688,
+                                                    "is_parallel": true,
+                                                    "self": 3.8605985319613865,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 8.51409830502007,
+                                                            "count": 23688,
+                                                            "is_parallel": true,
+                                                            "self": 8.51409830502007
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 117.28334450301236,
+                                                            "count": 23688,
+                                                            "is_parallel": true,
+                                                            "self": 117.28334450301236
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 9.195038524023403,
+                                                            "count": 23688,
+                                                            "is_parallel": true,
+                                                            "self": 3.241506134007068,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 5.953532390016335,
+                                                                    "count": 47376,
+                                                                    "is_parallel": true,
+                                                                    "self": 5.953532390016335
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 38.87117306500295,
+                            "count": 23689,
+                            "self": 0.7076474229975247,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 11.622941843005265,
+                                    "count": 23689,
+                                    "self": 11.46507861600503,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.15786322700023447,
+                                            "count": 1,
+                                            "self": 0.15786322700023447
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 26.54058379900016,
+                                    "count": 10,
+                                    "self": 20.773874048999915,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 5.7667097500002455,
+                                            "count": 270,
+                                            "self": 5.7667097500002455
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.229000190505758e-06,
+                    "count": 1,
+                    "self": 1.229000190505758e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.0007466710003427579,
+                    "count": 1,
+                    "self": 2.422400029900018e-05,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0007224470000437577,
+                            "count": 1,
+                            "self": 0.0007224470000437577
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,20 @@
+{
+    "Huggy": {
+        "checkpoints": [
+            {
+                "steps": 199992,
+                "file_path": "results/Huggy2/Huggy/Huggy-199992.onnx",
+                "reward": 3.495874868611158,
+                "creation_time": 1763310604.1128268,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-199992.pt"
+                ]
+            }
+        ]
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}